@inproceedings{fang-etal-2025-cart,
    title = "{CART}: A Generative Cross-Modal Retrieval Framework With Coarse-To-Fine Semantic Modeling",
    author = "Fang, Minghui  and
      Ji, Shengpeng  and
      Zuo, Jialong  and
      Huang, Hai  and
      Xia, Yan  and
      Zhu, Jieming  and
      Cheng, Xize  and
      Yang, Xiaoda  and
      Liu, Wenrui  and
      Wang, Gang  and
      Dong, Zhenhua  and
      Zhao, Zhou",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.acl-long.735/",
    pages = "15120--15133",
    ISBN = "979-8-89176-251-0"
}